{"total":13,"rows":[{"id":"2204.08110","title":"Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models","created":"2022-04-17","cited_by_count":92,"area":null},{"id":"2408.04303","title":"Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP","created":"2024-08-08","cited_by_count":36,"area":null},{"id":"2403.03814","title":"Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ","created":"2024-03-06","cited_by_count":27,"area":null},{"id":"2304.08823","title":"Transfer to a Low-Resource Language via Close Relatives: The Case Study on Faroese","created":"2023-04-18","cited_by_count":15,"area":null},{"id":"2310.03477","title":"Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2202.12312","title":"Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies","created":"2022-02-24","cited_by_count":9,"area":null},{"id":"2410.09644","title":"Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?","created":"2024-10-12","cited_by_count":9,"area":null},{"id":"2305.13026","title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2510.21954","title":"Model-Aware Tokenizer Transfer","created":"2025-10-24","cited_by_count":6,"area":null},{"id":"2409.10965","title":"Cross-lingual transfer of multilingual models on low resource African Languages","created":"2024-09-17","cited_by_count":5,"area":null},{"id":"2505.10945","title":"Semantic Aware Linear Transfer by Recycling Pre-trained Language Models for Cross-lingual Transfer","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2403.05257","title":"Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity","created":"2024-03-08","cited_by_count":1,"area":null},{"id":"2302.06120","title":"Knowledge from Large-Scale Protein Contact Prediction Models Can Be Transferred to the Data-Scarce RNA Contact Prediction Task","created":"2023-02-13","cited_by_count":0,"area":null}],"next_cursor":null}